13 files changed, 98 insertions, 81 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index b756f527497e..2e3f4a47e7d0 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -553,7 +553,7 @@ void acct_update_integrals(struct task_struct *tsk)
                 if (delta == 0)
                         return;
                 tsk->acct_stimexpd = tsk->stime;
-                tsk->acct_rss_mem1 += delta * get_mm_counter(tsk->mm, rss);
+                tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                 tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
         }
 }
diff --git a/kernel/audit.c b/kernel/audit.c
index aefa73a8a586..0c56320d38dc 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -133,7 +133,7 @@ struct audit_buffer {
         struct list_head     list;
         struct sk_buff       *skb;      /* formatted skb ready to send */
         struct audit_context *ctx;      /* NULL or associated context */
-        int                  gfp_mask;
+        gfp_t                gfp_mask;
 };
 
 static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
@@ -647,7 +647,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
  * will be written at syscall exit.  If there is no associated task, tsk
  * should be NULL. */
 
-struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
+struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
                                      int type)
 {
         struct audit_buffer     *ab     = NULL;
@@ -879,7 +879,7 @@ void audit_log_end(struct audit_buffer *ab)
 /* Log an audit record.  This is a convenience function that calls
  * audit_log_start, audit_log_vformat, and audit_log_end.  It may be
  * called in any context. */
-void audit_log(struct audit_context *ctx, int gfp_mask, int type, 
+void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, 
                const char *fmt, ...)
 {
         struct audit_buffer *ab;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 88696f639aab..d8a68509e729 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -803,7 +803,7 @@ static void audit_log_task_info(struct audit_buffer *ab)
         up_read(&mm->mmap_sem);
 }
 
-static void audit_log_exit(struct audit_context *context, unsigned int gfp_mask)
+static void audit_log_exit(struct audit_context *context, gfp_t gfp_mask)
 {
         int i;
         struct audit_buffer *ab;
diff --git a/kernel/exit.c b/kernel/exit.c
index 3b25b182d2be..79f52b85d6ed 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -839,7 +839,10 @@ fastcall NORET_TYPE void do_exit(long code)
                                 preempt_count());
 
         acct_update_integrals(tsk);
-        update_mem_hiwater(tsk);
+        if (tsk->mm) {
+                update_hiwater_rss(tsk->mm);
+                update_hiwater_vm(tsk->mm);
+        }
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
                 del_timer_sync(&tsk->signal->real_timer);
diff --git a/kernel/fork.c b/kernel/fork.c
index 280bd44ac441..8a069612eac3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -182,37 +182,37 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 }
 
 #ifdef CONFIG_MMU
-static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
+static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-        struct vm_area_struct * mpnt, *tmp, **pprev;
+        struct vm_area_struct *mpnt, *tmp, **pprev;
         struct rb_node **rb_link, *rb_parent;
         int retval;
         unsigned long charge;
         struct mempolicy *pol;
 
         down_write(&oldmm->mmap_sem);
-        flush_cache_mm(current->mm);
+        flush_cache_mm(oldmm);
+        down_write(&mm->mmap_sem);
+
         mm->locked_vm = 0;
         mm->mmap = NULL;
         mm->mmap_cache = NULL;
         mm->free_area_cache = oldmm->mmap_base;
         mm->cached_hole_size = ~0UL;
         mm->map_count = 0;
-        set_mm_counter(mm, rss, 0);
-        set_mm_counter(mm, anon_rss, 0);
         cpus_clear(mm->cpu_vm_mask);
         mm->mm_rb = RB_ROOT;
         rb_link = &mm->mm_rb.rb_node;
         rb_parent = NULL;
         pprev = &mm->mmap;
 
-        for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) {
+        for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
                 struct file *file;
 
                 if (mpnt->vm_flags & VM_DONTCOPY) {
                         long pages = vma_pages(mpnt);
                         mm->total_vm -= pages;
-                        __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
+                        vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
                                                                 -pages);
                         continue;
                 }
@@ -253,12 +253,8 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                 }
 
                 /*
-                 * Link in the new vma and copy the page table entries:
-                 * link in first so that swapoff can see swap entries.
-                 * Note that, exceptionally, here the vma is inserted
-                 * without holding mm->mmap_sem.
+                 * Link in the new vma and copy the page table entries.
                  */
-                spin_lock(&mm->page_table_lock);
                 *pprev = tmp;
                 pprev = &tmp->vm_next;
 
@@ -267,8 +263,7 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                 rb_parent = &tmp->vm_rb;
 
                 mm->map_count++;
-                retval = copy_page_range(mm, current->mm, tmp);
-                spin_unlock(&mm->page_table_lock);
+                retval = copy_page_range(mm, oldmm, tmp);
 
                 if (tmp->vm_ops && tmp->vm_ops->open)
                         tmp->vm_ops->open(tmp);
@@ -277,9 +272,9 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                         goto out;
         }
         retval = 0;
-
 out:
-        flush_tlb_mm(current->mm);
+        up_write(&mm->mmap_sem);
+        flush_tlb_mm(oldmm);
         up_write(&oldmm->mmap_sem);
         return retval;
 fail_nomem_policy:
@@ -323,6 +318,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
         INIT_LIST_HEAD(&mm->mmlist);
         mm->core_waiters = 0;
         mm->nr_ptes = 0;
+        set_mm_counter(mm, file_rss, 0);
+        set_mm_counter(mm, anon_rss, 0);
         spin_lock_init(&mm->page_table_lock);
         rwlock_init(&mm->ioctx_list_lock);
         mm->ioctx_list = NULL;
@@ -499,7 +496,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
         if (retval)
                 goto free_pt;
 
-        mm->hiwater_rss = get_mm_counter(mm,rss);
+        mm->hiwater_rss = get_mm_rss(mm);
         mm->hiwater_vm = mm->total_vm;
 
 good_mm:
diff --git a/kernel/futex.c b/kernel/futex.c
index ca05fe6a70b2..3b4d5ad44cc6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -205,15 +205,13 @@ static int get_futex_key(unsigned long uaddr, union futex_key *key)
         /*
          * Do a quick atomic lookup first - this is the fastpath.
          */
-        spin_lock(&current->mm->page_table_lock);
-        page = follow_page(mm, uaddr, 0);
+        page = follow_page(mm, uaddr, FOLL_TOUCH|FOLL_GET);
         if (likely(page != NULL)) {
                 key->shared.pgoff =
                         page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-                spin_unlock(&current->mm->page_table_lock);
+                put_page(page);
                 return 0;
         }
-        spin_unlock(&current->mm->page_table_lock);
 
         /*
          * Do it the general way.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index cdd4dcd8fb63..2c95848fbce8 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -90,7 +90,7 @@ int kexec_should_crash(struct task_struct *p)
 static int kimage_is_destination_range(struct kimage *image,
                                        unsigned long start, unsigned long end);
 static struct page *kimage_alloc_page(struct kimage *image,
-                                       unsigned int gfp_mask,
+                                       gfp_t gfp_mask,
                                        unsigned long dest);
 
 static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
@@ -326,8 +326,7 @@ static int kimage_is_destination_range(struct kimage *image,
         return 0;
 }
 
-static struct page *kimage_alloc_pages(unsigned int gfp_mask,
-                                        unsigned int order)
+static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
         struct page *pages;
 
@@ -335,7 +334,7 @@ static struct page *kimage_alloc_pages(unsigned int gfp_mask,
         if (pages) {
                 unsigned int count, i;
                 pages->mapping = NULL;
-                pages->private = order;
+                set_page_private(pages, order);
                 count = 1 << order;
                 for (i = 0; i < count; i++)
                         SetPageReserved(pages + i);
@@ -348,7 +347,7 @@ static void kimage_free_pages(struct page *page)
 {
         unsigned int order, count, i;
 
-        order = page->private;
+        order = page_private(page);
         count = 1 << order;
         for (i = 0; i < count; i++)
                 ClearPageReserved(page + i);
@@ -654,7 +653,7 @@ static kimage_entry_t *kimage_dst_used(struct kimage *image,
 }
 
 static struct page *kimage_alloc_page(struct kimage *image,
-                                        unsigned int gfp_mask,
+                                        gfp_t gfp_mask,
                                         unsigned long destination)
 {
         /*
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index d30b304a3384..bf374fceb39c 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -91,7 +91,7 @@ static inline union cpu_time_count cpu_time_sub(clockid_t which_clock,
  * Update expiry time from increment, and increase overrun count,
  * given the current clock sample.
  */
-static inline void bump_cpu_timer(struct k_itimer *timer,
+static void bump_cpu_timer(struct k_itimer *timer,
                                   union cpu_time_count now)
 {
         int i;
@@ -110,7 +110,7 @@ static inline void bump_cpu_timer(struct k_itimer *timer,
                 for (i = 0; incr < delta - incr; i++)
                         incr = incr << 1;
                 for (; i >= 0; incr >>= 1, i--) {
-                        if (delta <= incr)
+                        if (delta < incr)
                                 continue;
                         timer->it.cpu.expires.sched += incr;
                         timer->it_overrun += 1 << i;
@@ -128,7 +128,7 @@ static inline void bump_cpu_timer(struct k_itimer *timer,
                 for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
                              incr = cputime_add(incr, incr);
                 for (; i >= 0; incr = cputime_halve(incr), i--) {
-                        if (cputime_le(delta, incr))
+                        if (cputime_lt(delta, incr))
                                 continue;
                         timer->it.cpu.expires.cpu =
                                 cputime_add(timer->it.cpu.expires.cpu, incr);
@@ -380,14 +380,9 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 int posix_cpu_timer_del(struct k_itimer *timer)
 {
         struct task_struct *p = timer->it.cpu.task;
+        int ret = 0;
 
-        if (timer->it.cpu.firing)
-                return TIMER_RETRY;
-
-        if (unlikely(p == NULL))
-                return 0;
-
-        if (!list_empty(&timer->it.cpu.entry)) {
+        if (likely(p != NULL)) {
                 read_lock(&tasklist_lock);
                 if (unlikely(p->signal == NULL)) {
                         /*
@@ -396,18 +391,20 @@ int posix_cpu_timer_del(struct k_itimer *timer)
                          */
                         BUG_ON(!list_empty(&timer->it.cpu.entry));
                 } else {
-                        /*
-                         * Take us off the task's timer list.
-                         */
                         spin_lock(&p->sighand->siglock);
-                        list_del(&timer->it.cpu.entry);
+                        if (timer->it.cpu.firing)
+                                ret = TIMER_RETRY;
+                        else
+                                list_del(&timer->it.cpu.entry);
                         spin_unlock(&p->sighand->siglock);
                 }
                 read_unlock(&tasklist_lock);
+
+                if (!ret)
+                        put_task_struct(p);
         }
-        put_task_struct(p);
 
-        return 0;
+        return ret;
 }
 
 /*
@@ -424,8 +421,6 @@ static void cleanup_timers(struct list_head *head,
         cputime_t ptime = cputime_add(utime, stime);
 
         list_for_each_entry_safe(timer, next, head, entry) {
-                put_task_struct(timer->task);
-                timer->task = NULL;
                 list_del_init(&timer->entry);
                 if (cputime_lt(timer->expires.cpu, ptime)) {
                         timer->expires.cpu = cputime_zero;
@@ -437,8 +432,6 @@ static void cleanup_timers(struct list_head *head,
 
         ++head;
         list_for_each_entry_safe(timer, next, head, entry) {
-                put_task_struct(timer->task);
-                timer->task = NULL;
                 list_del_init(&timer->entry);
                 if (cputime_lt(timer->expires.cpu, utime)) {
                         timer->expires.cpu = cputime_zero;
@@ -450,8 +443,6 @@ static void cleanup_timers(struct list_head *head,
 
         ++head;
         list_for_each_entry_safe(timer, next, head, entry) {
-                put_task_struct(timer->task);
-                timer->task = NULL;
                 list_del_init(&timer->entry);
                 if (timer->expires.sched < sched_time) {
                         timer->expires.sched = 0;
@@ -495,6 +486,9 @@ static void process_timer_rebalance(struct task_struct *p,
         struct task_struct *t = p;
         unsigned int nthreads = atomic_read(&p->signal->live);
 
+        if (!nthreads)
+                return;
+
         switch (clock_idx) {
         default:
                 BUG();
@@ -503,7 +497,7 @@ static void process_timer_rebalance(struct task_struct *p,
                 left = cputime_div(cputime_sub(expires.cpu, val.cpu),
                                    nthreads);
                 do {
-                        if (!unlikely(t->exit_state)) {
+                        if (!unlikely(t->flags & PF_EXITING)) {
                                 ticks = cputime_add(prof_ticks(t), left);
                                 if (cputime_eq(t->it_prof_expires,
                                                cputime_zero) ||
@@ -518,7 +512,7 @@ static void process_timer_rebalance(struct task_struct *p,
                 left = cputime_div(cputime_sub(expires.cpu, val.cpu),
                                    nthreads);
                 do {
-                        if (!unlikely(t->exit_state)) {
+                        if (!unlikely(t->flags & PF_EXITING)) {
                                 ticks = cputime_add(virt_ticks(t), left);
                                 if (cputime_eq(t->it_virt_expires,
                                                cputime_zero) ||
@@ -533,7 +527,7 @@ static void process_timer_rebalance(struct task_struct *p,
                 nsleft = expires.sched - val.sched;
                 do_div(nsleft, nthreads);
                 do {
-                        if (!unlikely(t->exit_state)) {
+                        if (!unlikely(t->flags & PF_EXITING)) {
                                 ns = t->sched_time + nsleft;
                                 if (t->it_sched_expires == 0 ||
                                     t->it_sched_expires > ns) {
@@ -572,6 +566,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
         struct cpu_timer_list *next;
         unsigned long i;
 
+        if (CPUCLOCK_PERTHREAD(timer->it_clock) && (p->flags & PF_EXITING))
+                return;
+
         head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
                 p->cpu_timers : p->signal->cpu_timers);
         head += CPUCLOCK_WHICH(timer->it_clock);
@@ -582,17 +579,15 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
         listpos = head;
         if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
                 list_for_each_entry(next, head, entry) {
-                        if (next->expires.sched > nt->expires.sched) {
-                                listpos = &next->entry;
+                        if (next->expires.sched > nt->expires.sched)
                                 break;
-                        }
+                        listpos = &next->entry;
                 }
         } else {
                 list_for_each_entry(next, head, entry) {
-                        if (cputime_gt(next->expires.cpu, nt->expires.cpu)) {
-                                listpos = &next->entry;
+                        if (cputime_gt(next->expires.cpu, nt->expires.cpu))
                                 break;
-                        }
+                        listpos = &next->entry;
                 }
         }
         list_add(&nt->entry, listpos);
@@ -736,9 +731,15 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
          * Disarm any old timer after extracting its expiry time.
          */
         BUG_ON(!irqs_disabled());
+
+        ret = 0;
         spin_lock(&p->sighand->siglock);
         old_expires = timer->it.cpu.expires;
-        list_del_init(&timer->it.cpu.entry);
+        if (unlikely(timer->it.cpu.firing)) {
+                timer->it.cpu.firing = -1;
+                ret = TIMER_RETRY;
+        } else
+                list_del_init(&timer->it.cpu.entry);
         spin_unlock(&p->sighand->siglock);
 
         /*
@@ -786,7 +787,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
                 }
         }
 
-        if (unlikely(timer->it.cpu.firing)) {
+        if (unlikely(ret)) {
                 /*
                  * We are colliding with the timer actually firing.
                  * Punt after filling in the timer's old value, and
@@ -794,8 +795,6 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
                  * it as an overrun (thanks to bump_cpu_timer above).
                  */
                 read_unlock(&tasklist_lock);
-                timer->it.cpu.firing = -1;
-                ret = TIMER_RETRY;
                 goto out;
         }
 
@@ -1169,6 +1168,9 @@ static void check_process_timers(struct task_struct *tsk,
                 unsigned long long sched_left, sched;
                 const unsigned int nthreads = atomic_read(&sig->live);
 
+                if (!nthreads)
+                        return;
+
                 prof_left = cputime_sub(prof_expires, utime);
                 prof_left = cputime_sub(prof_left, stime);
                 prof_left = cputime_div(prof_left, nthreads);
@@ -1205,7 +1207,7 @@ static void check_process_timers(struct task_struct *tsk,
 
                         do {
                                 t = next_thread(t);
-                        } while (unlikely(t->exit_state));
+                        } while (unlikely(t->flags & PF_EXITING));
                 } while (t != tsk);
         }
 }
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 2d5c45676442..016504ccfccf 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -578,15 +578,23 @@ static int save_highmem_zone(struct zone *zone)
                         continue;
                 page = pfn_to_page(pfn);
                 /*
-                 * This condition results from rvmalloc() sans vmalloc_32()
-                 * and architectural memory reservations. This should be
-                 * corrected eventually when the cases giving rise to this
-                 * are better understood.
+                 * PageReserved results from rvmalloc() sans vmalloc_32()
+                 * and architectural memory reservations.
+                 *
+                 * rvmalloc should not cause this, because all implementations
+                 * appear to always be using vmalloc_32 on architectures with
+                 * highmem. This is a good thing, because we would like to save
+                 * rvmalloc pages.
+                 *
+                 * It appears to be triggered by pages which do not point to
+                 * valid memory (see arch/i386/mm/init.c:one_highpage_init(),
+                 * which sets PageReserved if the page does not point to valid
+                 * RAM.
+                 *
+                 * XXX: must remove usage of PageReserved!
                  */
-                if (PageReserved(page)) {
-                        printk("highmem reserved page?!\n");
+                if (PageReserved(page))
                         continue;
-                }
                 BUG_ON(PageNosave(page));
                 if (PageNosaveFree(page))
                         continue;
@@ -672,10 +680,9 @@ static int saveable(struct zone * zone, unsigned long * zone_pfn)
                 return 0;
 
         page = pfn_to_page(pfn);
-        BUG_ON(PageReserved(page) && PageNosave(page));
         if (PageNosave(page))
                 return 0;
-        if (PageReserved(page) && pfn_is_nosave(pfn)) {
+        if (pfn_is_nosave(pfn)) {
                 pr_debug("[nosave pfn 0x%lx]", pfn);
                 return 0;
         }
@@ -1095,7 +1102,7 @@ static inline void eat_page(void *page)
         *eaten_memory = c;
 }
 
-unsigned long get_usable_page(unsigned gfp_mask)
+unsigned long get_usable_page(gfp_t gfp_mask)
 {
         unsigned long m;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 1f31a528fdba..4f26c544d02c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2511,8 +2511,6 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
                 cpustat->idle = cputime64_add(cpustat->idle, tmp);
         /* Account for system time used */
         acct_update_integrals(p);
-        /* Update rss highwater mark */
-        update_mem_hiwater(p);
 }
 
 /*
@@ -3879,6 +3877,7 @@ EXPORT_SYMBOL(cpu_present_map);
 
 #ifndef CONFIG_SMP
 cpumask_t cpu_online_map = CPU_MASK_ALL;
+EXPORT_SYMBOL_GPL(cpu_online_map);
 cpumask_t cpu_possible_map = CPU_MASK_ALL;
 #endif
 
diff --git a/kernel/signal.c b/kernel/signal.c
index f2b96b08fb44..6904bbbfe116 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -406,6 +406,8 @@ void __exit_signal(struct task_struct *tsk)
 
 void exit_signal(struct task_struct *tsk)
 {
+        atomic_dec(&tsk->signal->live);
+
         write_lock_irq(&tasklist_lock);
         __exit_signal(tsk);
         write_unlock_irq(&tasklist_lock);
diff --git a/kernel/time.c b/kernel/time.c
index 40c2410ac99a..a3c2100470e1 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -532,6 +532,7 @@ int do_settimeofday (struct timespec *tv)
         clock_was_set();
         return 0;
 }
+EXPORT_SYMBOL(do_settimeofday);
 
 void do_gettimeofday (struct timeval *tv)
 {
diff --git a/kernel/timer.c b/kernel/timer.c
index 3ba10fa35b60..6a2e5f8dc725 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -752,6 +752,15 @@ static void second_overflow(void)
     else
         time_adj += (time_adj >> 2) + (time_adj >> 5);
 #endif
+#if HZ == 250
+    /* Compensate for (HZ==250) != (1 << SHIFT_HZ).
+     * Add 1.5625% and 0.78125% to get 255.85938; => only 0.05% error (p. 14)
+     */
+    if (time_adj < 0)
+        time_adj -= (-time_adj >> 6) + (-time_adj >> 7);
+    else
+        time_adj += (time_adj >> 6) + (time_adj >> 7);
+#endif
 #if HZ == 1000
     /* Compensate for (HZ==1000) != (1 << SHIFT_HZ).
      * Add 1.5625% and 0.78125% to get 1023.4375; => only 0.05% error (p. 14)